Background: Several studies demonstrated the feasibility of predicting bacterial antibiotic resistance phenotypes from whole-genome sequences, the prediction process usually amounting to detecting the presence of genes involved in antibiotic resistance mechanisms, or of specific mutations, previously identified from a training panel of strains, within these genes. We address the problem from the supervised statistical learning perspective, not relying on prior information about such resistance factors. We rely on a k-mer based genotyping scheme and a logistic regression model, thereby combining several k-mers into a probabilistic model. To identify a small yet predictive set of k-mers, we rely on the stability selection approach (Meinshausen et al., J R Stat Soc Ser B 72:417-73, 2010), that consists in penalizing logistic regression models with a Lasso penalty, coupled with extensive resampling procedures.
Results: Using public datasets, we applied the resulting classifiers to two bacterial species and achieved predictive performance equivalent to state of the art. The models are extremely sparse, involving 1 to 8 k-mers per antibiotic, hence are remarkably easy and fast to evaluate on new genomes (from raw reads to assemblies).
Conclusion: Our proof of concept therefore demonstrates that stability selection is a powerful approach to investigate bacterial genotype-phenotype relationships.
Keywords: Feature selection; Genotype-phenotype; Lasso; k-mers.